Bayesian Belief Network Modeling of Direct Numerically Simulated Imagery Variables for Sub-Surface Structure Diagnostics Nicholas V. Scott* a , and Tian-Jian Hsu b , Riverside Research Institute a , Dayton Research Center, 2640 Hibiscus Way, Dayton, OH 45431 University of Delaware b , Center for Applied Coastal Research, Newark, DE 19716 Abstract Naïve Bayesian belief network modeling is applied to direct numerically simulated imagery of oscillatory sediment- laden flow to illustrate the feasibility of creating a system model which captures the statistical interrelationship of the surface layer sediment concentration, pressure, and vertical velocity eddy scales with the sub-surface Reynolds stress. From a prognostic reasoning viewpoint, preliminary model results suggest that large sediment concentration eddy scales may result from the application of large positive Reynolds stress. However, from a diagnostic reasoning viewpoint, initial results suggest that robustly inferring sub-surface boundary layer stress from surface sediment concentration eddy scales may be a difficult task. The model formulism used allows for the ability to statistically characterize flow structure at depth from observations taken across a surface boundary layer, making the results relevant to image analysis at the air- sea interfacial boundary layer in large-scale coastal and riverine systems. Keywords: Direct numerical simulation, sediment-laden flow, sediment concentration eddy scales, velocity field eddy scales, pressure field eddy scales, Reynolds stress, Bayesian belief network, marginal probability distribution, conditional probability distribution, hard evidential instantiation. *nscott@riversideresearch.org; phone 937-427-7106, fax 937-429-0547